Engineering Commons^™

Bimodal Emotion Classification Using Deep Learning, Ashutosh Kumar Singh

Dissertations

Multimodal Emotion Recognition is an emerging associative field in the area of Human Computer Interaction and Sentiment Analysis. It extracts information from each modality to predict the emotions accurately. In this research, Bimodal Emotion Recognition framework is developed with the decision-level fusion of Audio and Video modality using RAVDES dataset. Designing such frameworks are computationally expensive and require more time to train the network. Thus, a relatively small dataset has been used for the scope of this research. The conducted research is inspired by the use of neural networks for emotion classification from multimodal data. The developed framework further confirmed …

Ensemble Lung Segmentation System Using Deep Neural Networks, Redha A. Ali, Russell C. Hardie, Hussin K. Ragb

Electrical and Computer Engineering Faculty Publications

Lung segmentation is a significant step in developing computer-aided diagnosis (CAD) using Chest Radiographs (CRs). CRs are used for diagnosis of the 2019 novel coronavirus disease (COVID-19), lung cancer, tuberculosis, and pneumonia. Hence, developing a Computer-Aided Detection (CAD) system would provide a second opinion to help radiologists in the reading process, increase objectivity, and reduce the workload. In this paper, we present the implementation of our ensemble deep learning model for lung segmentation. This model is based on the original DeepLabV3+, which is the extended model of DeepLabV3. Our model utilizes various architectures as a backbone of DeepLabV3+, such as …

Calibrating The Highway Capacity Manual Arterial Travel Time Reliability Model, Ernest Tufuor, Laurence Rilett, Li Zhao

Mid-America Transportation Center: Final Reports and Technical Briefs

The latest edition of the Highway Capacity Manual (HCM-6) includes, for the first time, a methodology for estimating and predicting the average travel time distribution (TTD) of urban streets. Travel time reliability (TTR) metrics can then be estimated from the TTD. The HCM-6 explicitly considers five key sources of travel time variability. A literature search showed no evidence that the HCM-6 TTR model has ever been calibrated with empirical travel time data. More importantly, previous research showed that the HCM-6 underestimated the empirical TTD variability by 70% on a testbed in Lincoln, Nebraska. In other words, the HCM-6 TTR metrics …

Analysis Of Component Errors In The Highway Capacity Manual Travel Time Reliability Estimations For Urban Streets, Ernest Tufuor, Laurence Rilett

Mid-America Transportation Center: Final Reports and Technical Briefs

The Highway Capacity Manual 6th edition (HCM6) includes a new methodology to estimate and predict the distribution of average travel times (TTD) for urban streets. The TTD can then be used to estimate travel time reliability (TTR) metrics. Previous research on a 0.5-mi testbed showed statistically significant differences between the HCM6 estimated TTD and the corresponding empirical TTD. The difference in average travel time was 4 s that, while statistically significant, is not important from a practical perspective. More importantly, the TTD variance was underestimated by 70%. In other words, the HCM6 results reflected a more reliable testbed than field …

Measuring The Occurrence Of Antibiotics In Surface Water Adjacent To Cattle Grazing Areas Using Passive Samplers, Nasrin Naderi Beni, Daniel D. Snow, Elaine D. Berry, Aaron R. Mittelstet, Tiffany Messer, Shannon L. Bartelt-Hunt

Nebraska Water Center: Faculty Publications

A wide variety of antibiotics and other pharmaceuticals are used in livestock production systems and residues passed to the environment, often unmetabolized, after use and excretion. Antibiotic residuesmay be transported frommanure-treated soils via runoff and are also capable of reaching surface and groundwater systems through a variety of pathways. The occurrence and persistence of antibiotics in the environment is a concern due to the potential for ecological effects and proliferation of environmental antibiotic resistance in pathogenic organisms. In the present study, the occurrence and seasonal variation of 24 commonly-used veterinary antibiotics was evaluated in surface water adjacent to several livestock …

Fabrication Of Dielectric Elastomers With Improved Electromechanical Properties Using Silicone Rubber And Walnut Polyphenols Modified Dielectric Particles, Liang Jiang, Yuhao Wang, Shipeng Wen, Yanfen Zhou, Qingdao University, Stephen Jerrams

Articles

In this work, polyphenolic extract from walnut green husks (denoted as walnut polyphenols), which is an abun-dant agroindustrial residue/waste, was used to modify barium titanate (BT) particles in the preparation of sili-cone rubber (SR) based dielectric elastomer (DE) composites with enhanced electromechanical performance.By employing walnut polyphenols modification, the dispersibility of BT particles in the SR matrix and the com-patibility between BT and SR were greatly improved, which resulted in enhanced mechanical performance ofthe DE composites. Dielectric property measurement showed that DE composites containing walnut polyphenolsmodified BT particles (WNBT) had higher dielectric constants and lower dielectric losses than that of DEs …

Lm-Based Word Embeddings Improve Biomedical Named Entity Recognition: A Detailed Analysis, Liliya Akhtyamova, John Cardiff

Conference Papers

Recent studies have shown that contextualized word embeddings outperform other types of embeddings on a variety of tasks. However, there is little research done to evaluate their effectiveness in the biomedical domain under multi-task settings. We derive the contextualized word embeddings from the Flair framework and apply them to the task of biomedical NER on 5 benchmark datasets, yielding major improvements over the baseline and achieving competitive results over the current best systems. We analyze the sources of these improvements, reporting model performances over different combinations of word embeddings, and fine-tuning and casing modes.

Short-Term Truckload Spot Rates' Prediction In Consideration Of Temporal And Between-Route Correlations, Wei Xiao, Chuan Xu, Hongling Liu, Hong Yang, Xiaobo Liu

Computational Modeling & Simulation Engineering Faculty Publications

Truckload spot rate (TSR), defined as a price offered on the spot to transport a certain cargo by using an entire truck on a target transportation line, usually price per kilometer-ton, is a key factor in shaping the freight market. In particular, the prediction of short-term TSR is of great importance to the daily operations of the trucking industry. However, existing predictive practices have been limited largely by the availability of multilateral information, such as detailed intraday TSR information. Fortunately, the emerging online freight exchange (OFEX) platforms provide unique opportunities to access and fuse more data for probing the trucking …

Recent Developments In The General Atomic And Molecular Electronic Structure System, Guiseppe M.J. Barca, Colleen Bertoni, Laura Carrington, Dipayan Datta, Nuwan De Silva, J. Emillano Deustua, Dmitri G. Fedorov, Jeffrey R. Cour, Anastasia O. Gunina, Emilie Guidez, Taylor Harville, Stephan Irle, Joe Ivanic, Karol Kowalski, Sarom S. Leang, Wei Li, Jesse J. Lutz, Ilias Magoulas, Joani Mato, Vladimir Mironov, Hiroya Nakata, Buu Q. Pham, Piotr Piecuch, David Poole, Spencer R. Pruitt, Alistair P. Rendell, Luke B. Roskop, Klaus Ruedenberg, Tosaporn Sattasathuchana, Michael W. Schmidt, Jun Shen, Lyudmila Slipchenko, Masha Sosonkina, Vaibhav Sundriyal, Ananta Tiwari, Jorge L. Galvez Vallejo, Bryce Westheimer, Marta Włoch, Peng Xu, Federico Zahariev, Mark S. Gordon

Computational Modeling & Simulation Engineering Faculty Publications

A discussion of many of the recently implemented features of GAMESS (General Atomic and Molecular Electronic Structure System) and LibCChem (the C++ CPU/GPU library associated with GAMESS) is presented. These features include fragmentation methods such as the fragment molecular orbital, effective fragment potential and effective fragment molecular orbital methods, hybrid MPI/OpenMP approaches to Hartree-Fock, and resolution of the identity second order perturbation theory. Many new coupled cluster theory methods have been implemented in GAMESS, as have multiple levels of density functional/tight binding theory. The role of accelerators, especially graphical processing units, is discussed in the context of the new features …

Illuminator, Volume 3, Issue 5, Batten College Of Engineering & Technology, Old Dominion University

College of Engineering & Technology Newsletter

January 2020 issue of Illuminator, a monthly publication of ODU's Batten College of Engineering and Technology.

Deformable Multisurface Segmentation Of The Spine For Orthopedic Surgery Planning And Simulation, Rabia Haq, Jérôme Schmid, Roderick Borgie, Joshua Cates, Michel Audette

Computational Modeling & Simulation Engineering Faculty Publications

Purpose: We describe a shape-aware multisurface simplex deformable model for the segmentation of healthy as well as pathological lumbar spine in medical image data.

Approach: This model provides an accurate and robust segmentation scheme for the identification of intervertebral disc pathologies to enable the minimally supervised planning and patient-specific simulation of spine surgery, in a manner that combines multisurface and shape statistics-based variants of the deformable simplex model. Statistical shape variation within the dataset has been captured by application of principal component analysis and incorporated during the segmentation process to refine results. In the case where shape statistics hinder detection …

Implementing Asynchronous Linear Solvers Using Non-Uniform Distributions, Erik Jensen, Evan C. Coleman, Masha Sosonkina

Computational Modeling & Simulation Engineering Faculty Publications

Asynchronous iterative methods present a mechanism to improve the performance of algorithms for highly parallel computational platforms by removing the overhead associated with synchronization among computing elements. This paper considers a class of asynchronous iterative linear system solvers that employ randomization to determine the component update orders, specifically focusing on the effects of drawing the order from non-uniform distributions. Results from shared-memory experiments with a two-dimensional finite-difference discrete Laplacian problem show that using distributions favoring the selection of components with a larger contribution to the residual may lead to faster convergence than selecting uniformly. Multiple implementations of the randomized asynchronous …

Toilet Alarms: A Novel Application Of Latrine Sensors And Machine Learning For Optimizing Sanitation Services In Informal Settlements, Phillip Nicholas Turman-Bryant, Taylor Sharpe, Corey L. Nagel, Lauren Stover, Evan A. Thomas

Systems Engineering Faculty Publications and Presentations

The cost-effectiveness and reliability of waste collection services in informal settlements can be difficult to optimize given the geospatial and temporal variability of latrine use. Daily servicing to avoid overflow events is inefficient, but dynamic scheduling of latrine servicing could reduce costs by providing just-in-time servicing for latrines. This study used cellular-connected motion sensors and machine learning to dynamically predict when daily latrine servicing could be skipped with a low risk of overflow. Sensors monitored daily latrine activity, and enumerators collected solid and liquid waste weight data. Given the complex relationship between latrine use and the need for servicing, an …

Systematic Errors In Video Analysis, Tim Martin, Kayt E. Frisch, John Zwart

Faculty Publications - Biomedical, Mechanical, and Civil Engineering

Video analysis helps students to connect physical, mathematical, and graphical models with the phenomena that the models represent and improves student kinematic graph interpretation skills. The widespread availability of easy to use software packages like Logger Pro (Vernier), Capstone (PASCO), and Tracker have led to many introductory physics courses adopting video analysis techniques in the classroom. Such uses include high-speed cameras to study rocket launches and other innovative applications. In this paper, we will look at ways in which some common systematic errors can affect outcomes.

Effect Of Subsurface Microseismicity On The Motion Of Surrounding Dispersed Droplets -- Data, Chao Zeng, Wen Deng

Effect of Subsurface Microseismicity on the Motion of Surrounding Dispersed Droplets – Data

Spreadsheet - Data plotted in Figure 4 and Figure 5

Supporting information

Composite Guitar, Ryn Rollins

All Undergraduate Projects

Traditional wood-bodied products such as boats, hockey sticks, and guitars can be easily chipped or cracked if not properly taken care of. The wood can absorb moisture and deteriorate over time. If that wood is replaced with composite materials, those products can become stronger, more lightweight, and resistant to temperature and corrosion. Two of the most popular composite materials are carbon fiber and fiberglass. Because these composite materials have such a high strength, the core of a guitar body can also be replaced with a lighter material such as Styrofoam which makes for a lighter and more durable guitar. The …

Perceived Neighborhood: Preferences Versus Actualities, Saeed Moradi, Ali Nejat, Da Hu, Souparno Ghosh

Department of Statistics: Faculty Publications

Housing recovery plays a key role in the overall restoration of a community. A multitude of factors affect housing recovery, many of which are associated with interactions of residents with their perceived neighborhoods. Targeting perceived neighborhoods rather than administratively defined measures of land helps with devising recovery plans that could better address social preferences of the residents. However, such measures are commonly subject to collection of information via expensive and time-consuming surveys. The current research aims to contribute to the domain by exploring the relationship between perception of households of their neighborhood anchors (perceived anchors) and the anchors that exist …

Negative Curvature Hollow Core Fiber Based All-Fiber Interferometer And Its Sensing Applications To Temperature And Strain, Dejun Liu, Wei Li, Qiang Wu, Haoyu Zhao, Fengzi Ling, Ke Tian, Changyu Shen, Fangfang Wei, Wei Han, Gerald Farrell, Yuliya Semenova, Pengfei Wang

Articles

Negative curvature hollow core fiber (NCHCF) is a promising candidate for sensing applications; however, research on NCHCF based fiber sensors starts only in the recent two years. In this work, an all-fiber interferometer based on an NCHCF structure is proposed for the first time. The interferometer was fabricated by simple fusion splicing of a short section of an NCHCF between two singlemode fibers (SMFs). Both simulation and experimental results show that multiple modes and modal interferences are excited within the NCHCF structure. Periodic transmission dips with high spectral extinction ratio (up to 30 dB) and wide free spectral range (FSR) …

Nis2 As A Broadband Saturable Absorber For Ultrafast Pulse Lasers, Pengfei Wang, Han Zhang, Yu Yin, Qiuyun Ouyang, Yujin Chen, Elfed Lewis, Gerald Farrell, Masaki Tokurakawa, Sulaiman Wadi Harun, Cong Wang, Shi Li

Articles

Nickel disulfide (NiS2) has recently been found to possess strong nonlinear saturable absorption properties. This feature is highly attractive for nonlinear photonics applications. Ultrafast pulse generation is successfully demonstrated in this article for both Ytterbium- and Erbium-doped fibre lasers using micro-fibre deposited nickel disulfide (NiS2) as a saturable absorber (SA). The fabricated SA device has a modulation depth of 23% at 1.06 μm and 30.8% at 1.55 μm. Stable dissipative soliton operation was achieved at 1064.5 nm with a pulse duration of 11.7 ps and another stable conventional soliton pulse train was also obtained at 1560.2 nm with a pulse …

Intense Mid-Infrared Emission At 3.9 Μm In Ho3+-Doped Zbya Glasses For Potential Use As A Fiber Laser, Haiyan Zhao, Ruicong Wang, Xin Wang, Shijie Jia, Yaxian Fan, Elfed Lewis, Gerald Farrell, Shunbin Wang, Pengfei Wang

Articles

Intense mid-infrared emission at 3.9 µm in Ho3+-doped ZBYA glasses with direct upper laser level (Ho3+ : 5 I5) pumping at a wavelength of 888 nm is reported for the first time, to the best of our knowledge. Spectroscopic parameters were determined using the Judd–Ofelt theory and the measured absorption spectrum. The maximum emission cross section of the Ho3+-doped ZBYA glass is estimated to be 2.7 × 10−21 cm2 at 3906 nm. Additionally, fluorescence spectra and lifetimes of ZBYA glasses with different Ho3+ ion doping concentrations were measured. The results provide theoretical and experimental basis for better selection of rare-earth-doped …

Gender-Related Differences In Flood Risk Perception And Behaviours Among Private Groundwater Users In The Republic Of Ireland, Cillian P. Mcdowell, Luisa Andrade, Eoin O'Neill, Kevin O'Malley, Jean O'Dwyer, Paul Hynds

Articles

Extreme weather events including flooding can have severe personal, infrastructural, and economic consequences, with recent evidence pointing to surface flooding as a pathway for the microbial contamination of private groundwater supplies. There is a pressing need for increasingly focused information and awareness campaigns to highlight the risks posed by extreme weather events and appropriate subsequent post-event actions. To date, little is known about the presence, directionality or magnitude of gender-related differences regarding flood risk awareness and behaviour among private groundwater users, a particularly susceptible sub-population due to an overarching paucity of infrastructural regulation across many regions. The current study investigated …

A Discrimination Aware Model To Predict Childhood Literacy Levels, Kate Byrne

Dissertations

It is illegal in Ireland to discriminate in the provision of education on the basis of multiple characteristics including gender, race and religion. While the increased use of machine learning models can open multiple avenues to identify early intervention strategies in education, caution must be exercised to ensure that any intervention does not discriminate with respect to a protected class. Poor literacy in childhood can have long term effects as the child ages, including on employment and mental health outcomes. Early intervention is key in mitigating this. In this dissertation, a model was created that predicted the outcome of a …

An Evaluation Of Text Representation Techniques For Fake News Detection Using: Tf-Idf, Word Embeddings, Sentence Embeddings With Linear Support Vector Machine., Sangita Sriram

Dissertations

In a world where anybody can share their views, opinions and make it sound like these are facts about the current situation of the world, Fake News poses a huge threat especially to the reputation of people with high stature and to organizations. In the political world, this could lead to opposition parties making use of this opportunity to gain popularity in their elections. In the medical world, a fake scandalous message about a medicine giving side effects, hospital treatment gone wrong or even a false message against a practicing doctor could become a big menace to everyone involved in …

Drug Reviews: Cross-Condition And Cross-Source Analysis By Review Quantification Using Regional Cnn-Lstm Models, Ajith Mathew Thoomkuzhy

Dissertations

Pharmaceutical drugs are usually rated by customers or patients (i.e. in a scale from 1 to 10). Often, they also give reviews or comments on the drug and its side effects. It is desirable to quantify the reviews to help analyze drug favorability in the market, in the absence of ratings. Since these reviews are in the form of text, we should use lexical methods for the analysis. The intent of this study was two-fold: First, to understand how better the efficiency will be if CNN-LSTM models are used to predict ratings or sentiment from reviews. These models are known …

Deep Direct Use Geothermal Energy In The North Dakota Clean Energy Transition Strategy, Al Thibeault, Moones Alamooti, Nnaemeka Ngobidi, Will Gosnold

Geology and Geological Engineering Faculty Publications

The geothermal heat in the Williston Basin is an energy giant that can provide sustainable, renewable, and ecologically sound heat and power for the state of North Dakota (ND). We have known of this resource for decades, but development has been delayed for reasons which can be summed as economic competition from existing fossil fuel energy sources. With the “seismic” shock of the Covid-19 pandemic reverberating through the state’s carbon-centric economy, the timing is ideal for acting quickly to develop this energy resource.

Coincidentally, the State Energy Research Center (SERC) within the Energy & Environmental Research Center (EERC), has recently …

Adapting Microservices In The Cloud With Faas, Mateusz Pietraszewski

Dissertations

This project involves benchmarking, microservices and Function-as-a-service (FaaS) across the dimensions of performance and cost. In order to do a comparison this paper proposes a benchmark framework.

Lightgwas: A Novel Genome-Wide Association Study Procedure, Bruno Ambrozio

Dissertations

This dissertation proposes LightGWAS, a novel machine learning procedure for genome-wide association study (GWAS) based on LightGBM and k-fold cross-validation. The conducted literature review identified that the currently available GWAS implementations rely on massive manual quality control steps to address statistical issues, such as controlling for false-positive inflation and power reduction. It also showed they demand a specific GWAS method for each type of genomic dataset morphology, which consequently increases the human dependency and open margins for misleadings. LightGWAS is a potential single, resilient, autonomous and scalable solution to address such concerns. Through this research, LightGWAS was contrasted against the …

Rc Mini Baja Car - Suspension And Chassis, Collin Mckenzie

All Undergraduate Projects

Two students have developed a unique design of the RC Baja Car to optimize functionality and performance. A Baja car is a remote controlled 1/10 scale car that is used for recreation or competition, usually meant for competing in the ASME Baja car competition versus various schools. The competition focuses on the best time achieved in different courses that utilize speed, turns, and jumps. The objective for the project was to create a unique suspension from previous individual’s projects by creating a four-link suspension in which allows more travel in the suspension of the car and maintains functionality with the …

H.F. Hauff Portable Wind Fan Stabilizer, Tyler Hoffman

All Undergraduate Projects

Agricultural areas with cold weather in winter and early spring face significant risk of damage to crops due to freezing. To combat this issue, several farms use fans to keep goods from freezing. For some orchards and vineyards, the use of large-scale fans is not cost effective nor pragmatic. H.F. Hauff, a farming equipment company based out of Yakima, Washington, has developed a mobile, self-contained fan that operates on a seven-by-twelve-foot trailer. As a function of environment, the trailer sometimes operates on uneven or unlevel terrain. There arises a need for an improved outrigger system to keep the trailer stabilized. …

Physical Randomness Can Help In Computations, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

Can we use some so-far-unused physical phenomena to compute something that usual computers cannot? Researchers have been proposing many schemes that may lead to such computations. These schemes use different physical phenomena ranging from quantum-related to gravity-related to using hypothetical time machines. In this paper, we show that, in principle, there is no need to look into state-of-the-art physics to develop such a scheme: computability beyond the usual computations naturally appears if we consider such a basic notion as randomness.